Record your screen, ship a demo. Free and open-source, GPU-accelerated, no watermarks, no subscriptions. Windows, macOS, Linux. Actively maintained.
TypeScript cross-platformelectronffmpegopen-sourceproduct-demorustscreen-capturescreen-recorderscreen-recordingscreen-studioscreencastspeech-to-texttypescriptvideo-editingvideo-editorwaylandwgpuwhisper
docs(mcp): one tool surface on both transports
EtienneLescot1571b9937003
diff --git a/skills/openscreen-demo/SKILL.md b/skills/openscreen-demo/SKILL.mdindex 20c9ce43d..a88b499ae 100644--- a/skills/openscreen-demo/SKILL.md+++ b/skills/openscreen-demo/SKILL.md@@ -12,7 +12,7 @@ You produce a short MP4 that shows one feature, zooms on the action and carries## 1. Set up OpenScreen-You need the tools `startRecording`, `stopRecording`, `exportVideo` and `getFrames`. If you have them, go to step 2. Otherwise set OpenScreen up, once per machine, doing only what is missing.+You need the tools `startRecording`, `stopRecording`, `exportVideo` and `getFrames`. Both of OpenScreen's MCP servers have them: the one the app serves (*AI settings* → *MCP server*), and `openscreen mcp`, set up below. If you have them, go to step 2. Otherwise set OpenScreen up, once per machine, doing only what is missing.**The app.** Its executable is the MCP server:@@ -60,7 +60,7 @@ Write a storyboard and show it to the user in a few lines, then carry on unless## 4. Record-1. `startRecording` with `window`. It returns once capture has started.+1. `startRecording` with `window`. It returns once capture has started. Connected to the server in the app, the take goes through OpenScreen's recording bar: the editor closes, the bar counts down, and `stopRecording` opens the take in the editor.2. Play the storyboard. Move deliberately, and pause about one second after each result appears.3. `stopRecording` with a `title`. Keep what it returns: `projectId`, `checkpointId`, `videoPath`, `recordingStartedAt`.@@ -89,7 +89,7 @@ Keep the rest as it is: the background, padding, shadow and cursor style are cho## 7. Export and review-1. `exportVideo` with the `projectId` and a path such as `demo/demo.mp4`. For a pull request video, pass `quality: "medium"` (720p) to keep the file small.+1. `exportVideo` with the `projectId` and the absolute path of, say, `demo/demo.mp4` in the working directory: the server in the app takes only absolute paths. For a pull request video, pass `quality: "medium"` (720p) to keep the file small.2. `getFrames` with the `projectId`, at the ruler seconds of your beats.3. Check every frame:- Is each callout readable and clear of the action?@@ -129,6 +129,7 @@ Only to a pull request the user asked for a video on, or one you open for them i## When it goes wrong- **`The recording did not start`:** the window title did not match, or capture is not permitted. Check `listSources` and the permissions in step 1.+- **Recording, exporting or an edit refused, naming *MCP edits*:** you are connected to the server in the app, which records, exports and edits only once the user allows it. Ask them to turn on *MCP edits* under *AI settings* → *MCP server*.- **No cursor in the video:** the app was driven by a script. See step 4.- **No zoom on an early click:** the first 2.5 s stay wide on purpose. Start the first action after that.- **`unknown flag: --attach`:** `gh` is older than 2.99.0. See step 8.diff --git a/technical-documentation/architecture/mcp-server.md b/technical-documentation/architecture/mcp-server.mdindex 78547b010..5a3c56a2d 100644--- a/technical-documentation/architecture/mcp-server.md+++ b/technical-documentation/architecture/mcp-server.md@@ -9,10 +9,11 @@ The same tools are served over two transports, by two different processes:| Process | The running app (the GUI) | A process of its own, started by the client: the app's executable with `mcp` || Setup | **AI settings → MCP server**: turn it on, copy the `claude mcp add` / `codex mcp add` command (it carries the token) | `claude mcp add openscreen -- <executable> mcp` ([executables](../../website/docs/cli.md#running-the-cli)) || Auth | Bearer token, `127.0.0.1` only, Host/Origin check | None: the client launched the process with the user's rights |-| Edits | Off until the user turns on **MCP edits** | Always allowed |+| Edits, recording, export | Off until the user turns on **MCP edits** | Always allowed || Project open in the editor | Edited live through the editor, one undo step per call | The same while the app runs: the call is forwarded to it. With no app answering, refused ([the marker](#the-open-in-editor-marker)) || Other projects | Read from and saved to their file, a checkpoint first | Same |-| Tools | `listProjects`, the agent's tools, the checkpoint tools | The same, plus the media tools: `listSources`, `startRecording`, `stopRecording`, `setPointerTrack`, `exportVideo`, `getFrames` |+| Tools | `listProjects`, the agent's tools, the checkpoint tools, and the media tools: `listSources`, `startRecording`, `stopRecording`, `setPointerTrack`, `exportVideo`, `getFrames` | The same |+| A take | Recorded by the app's recording bar, as its Record button records; the editor opens it ([below](#the-media-tools)) | Recorded by a hidden runner of its own process, and made a project there || Checkpoints | In the app's memory, shared with forwarded `openscreen mcp` calls, lost when the app quits | In the app's while it runs; otherwise in this process's, lost when it exits, which it does when the client disconnects |**When the app runs, it is the authority**: `openscreen mcp` forwards its document calls to it ([below](#openscreen-mcp-and-the-running-app)), so one process writes the projects. Only when no app answers do two processes write the same project folder; the [open-in-editor marker](#the-open-in-editor-marker) and the byte compare of `saveProjectIfUnchanged` are then what keep them from overwriting each other's work.@@ -20,8 +21,9 @@ The same tools are served over two transports, by two different processes:| File | Role ||---|---|| [`electron/mcp/openscreen-mcp-server.ts`](../../electron/mcp/openscreen-mcp-server.ts) | The tools both transports serve, the tool runner (routing, refusals, checkpoints), the texts per transport (`mcpInstructions`), and the local HTTP guard. |-| [`electron/mcp/stdio-server.ts`](../../electron/mcp/stdio-server.ts) | `openscreen mcp`: the same server and runner on stdin/stdout, with the media tools. |-| [`electron/mcp/media-tools.ts`](../../electron/mcp/media-tools.ts) | The media tools and their capability block (`MEDIA_PREAMBLE`). |+| [`electron/mcp/stdio-server.ts`](../../electron/mcp/stdio-server.ts) | `openscreen mcp`: the same server, runner and media tools on stdin/stdout. |+| [`electron/mcp/media-tools.ts`](../../electron/mcp/media-tools.ts) | The media tools both servers serve (`createMediaTools`), their capability block per transport (`mediaPreamble`), and `openscreen mcp`'s recorder. |+| [`electron/mcp/app-recorder.ts`](../../electron/mcp/app-recorder.ts) | The in-app server's recorder: a take through the app's recording bar, opened by its editor. || [`electron/mcp/editor-document-host.ts`](../../electron/mcp/editor-document-host.ts) | Main-process side of the live document: asks the editor window for a snapshot and hands edits back. || [`electron/mcp/app-channel.ts`](../../electron/mcp/app-channel.ts) | The local channel `openscreen mcp` forwards its document calls through to the running app. See [`openscreen mcp` and the running app](#openscreen-mcp-and-the-running-app). || [`electron/mcp/mcp-controller.ts`](../../electron/mcp/mcp-controller.ts) | In-app server lifecycle: start when enabled, restart on a port or token change, status for the settings UI. |@@ -33,7 +35,7 @@ The same tools are served over two transports, by two different processes:Nothing about the tools is reimplemented. The server registers `TOOL_ARG_SCHEMAS` (names and zod schemas) and `TOOL_DESCRIPTIONS`, and builds its `instructions` around `buildSystemPrompt`, all exported from [`deep-agent/service.ts`](../../electron/ai-edition/deep-agent/service.ts), where `buildTools` builds the in-app agent from the same table. Every call goes through `runDocumentTool`, the function the in-app agent's `documentTool` also calls: the cursor-telemetry read the zoom tools need, then `executeAgentTool`.-So a tool added to the agent appears over MCP with no further work, and the MCP test asserts the listed tools equal `listProjects`, then `OPENSCREEN_TOOL_NAMES`, then the two checkpoint tools below. What the server adds:+So a tool added to the agent appears over MCP with no further work, and the MCP test asserts the listed tools equal `listProjects`, then `OPENSCREEN_TOOL_NAMES`, then the two checkpoint tools, then the [media tools](#the-media-tools). What the server adds:- **`listProjects`**, a tool of its own: every project's id, title, `updatedAt`, asset count, and `open` for the one in an editor (this process's, or the app's seen through the marker).- **An optional `projectId` on every agent tool and both checkpoint tools**, added to its schema with `.extend()` at registration and stripped again before the call reaches the executor, which never sees it. See [Which project a call acts on](#which-project-a-call-acts-on).@@ -44,14 +46,16 @@ So a tool added to the agent appears over MCP with no further work, and the MCPEvery text a client reads must be true on the server that serves it, so the texts are composed rather than shared verbatim. `McpToolDeps.transport` (`"http"` or `"stdio"`) selects them:-- **Instructions** (`mcpInstructions`): the media tools' capability block when they are registered, then the projects-and-checkpoints rules of the transport, then how long checkpoints live there, then `buildSystemPrompt`. The checkpoint rule is in both. Over HTTP the rules speak of the editor and its undo stack and add "Nothing here records, exports or imports media"; over stdio they say that calls go through the app while it runs (the open project live, with `Ctrl/Cmd+Z`), and to the files when it does not.-- **`buildSystemPrompt`** takes the transport's facts as options: `editsSetting` names the switch its consent block points to (the MCP server's **MCP edits**, not the in-app agent's **Agent edits**), and `canExport` drops "exporting" from its examples of a request with no tool when `exportVideo` is served.-- **Tool descriptions**: `projectId` is "omit it for the open project" over HTTP and "omit it only for the open project, while the app runs" over stdio; `restoreCheckpoint` mentions the pointer track only where `setPointerTrack` is served.+- **Instructions** (`mcpInstructions`): the media tools' capability block (`mediaPreamble`), then the projects-and-checkpoints rules of the transport, then how long checkpoints live there, then `buildSystemPrompt`. The checkpoint rule is in both. Over HTTP the media block says a take goes through the app's recording bar and opens in the editor, and the rules speak of the editor and its undo stack; while **MCP edits** is off, a line says `startRecording` and `exportVideo` are refused too. Over stdio the media block says the takes land in the app's project list, and the rules say that calls go through the app while it runs (the open project live, with `Ctrl/Cmd+Z`), and to the files when it does not.+- **`buildSystemPrompt`** takes the transport's facts as options: `editsSetting` names the switch its consent block points to (the MCP server's **MCP edits**, not the in-app agent's **Agent edits**), and `canExport` drops "exporting" from its examples of a request with no tool, since both serve `exportVideo`.+- **Tool descriptions**: `projectId` is "omit it for the open project" over HTTP and "omit it only for the open project, while the app runs" over stdio. `startRecording` and `stopRecording` say how each server makes a take ([below](#the-media-tools)), and the paths of `exportVideo` and `getFrames` must be absolute over HTTP: the app has no working directory of the client's.- **Messages**: no project to fall back on, a checkpoint required, an unknown checkpoint, edits turned off. Each has a version per transport, or exists only on the one that can produce it. The stdio versions are only met with no app answering, and say so.-The in-app chat agent keeps `buildSystemPrompt`'s defaults: its own switch, no export.+The in-app chat agent keeps `buildSystemPrompt`'s defaults: its own switch, no export. The app's channel for `openscreen mcp` registers no media tools, so its instructions have no media block: no agent reads them.-**Writes on the in-app server are a second opt-in.** MCP clients have their own **MCP edits** switch, `allowEdits` in `mcp-server.json`, **off by default** and independent of the in-app agent's **Agent edits** (`allowAgentEdits`). Turning the server on therefore grants read access only. The value is read on every call; while it is off every mutating tool and `setPointerTrack` are refused with the executor's `consent_required` payload naming **MCP edits**, `restoreCheckpoint` with its own refusal text naming it too, and the consent block of the system prompt is in the instructions. It is independent because `allowAgentEdits` defaults to allowed and lives in the provider form, so a user with no provider configured could never have turned MCP writes off. Toggling it does not restart the server. `openscreen mcp` has no such switch: the client started it itself, and there is no other caller to keep out. Its calls forwarded to the app keep that: the runner takes `editsAllowed` per call.+**Writes on the in-app server are a second opt-in.** MCP clients have their own **MCP edits** switch, `allowEdits` in `mcp-server.json`, **off by default** and independent of the in-app agent's **Agent edits** (`allowAgentEdits`). Turning the server on therefore grants read access only. The value is read on every call; while it is off every mutating tool and `setPointerTrack` are refused with the executor's `consent_required` payload naming **MCP edits**, `restoreCheckpoint` with its own refusal text naming it too, `startRecording` and `exportVideo` with theirs, and the consent block of the system prompt is in the instructions. It is independent because `allowAgentEdits` defaults to allowed and lives in the provider form, so a user with no provider configured could never have turned MCP writes off. Toggling it does not restart the server. `openscreen mcp` has no such switch: the client started it itself, and there is no other caller to keep out. Its calls forwarded to the app keep that: the runner takes `editsAllowed` per call.++**Recording and export wait for the same switch, with no setting of their own.** The settings model has two steps: the server on is read access, **MCP edits** on is a client changing things. A take captures the screen and creates a project; an export writes a file wherever the client says, over one already there. Both change things, more than an edit does, so both wait for **MCP edits**, whose label says so: *Allow MCP clients to edit your projects, record and export*. A third switch would split one decision, whether this client may act for the user, in two. `stopRecording` is not gated, so a take started before the switch went off can still end. `listSources` and `getFrames` only read, so the server being on is enough.## Which project a call acts on@@ -112,13 +116,25 @@ A client chains several edits in one turn, and each is its own undo step, so rev- It discards every edit since the checkpoint, the user's included. The tool description says so.- **Lifetime.** Checkpoints live in the runner's memory, the 20 most recent. In the app that is one runner (`createToolRunner`, built in `registerIpcHandlers`), shared by the in-app server and every forwarded `openscreen mcp` call; a restart of the in-app server keeps them, and they are lost when the app quits. An `openscreen mcp` with no app answering keeps its own, lost when the process exits, which it does when the client disconnects. The unknown-checkpoint message says which. The in-app agent does not need them: its whole turn is a single apply.-## The media tools (stdio)+## The media tools++`createMediaTools` builds the tools that make a video around the edits, once per server, and `createOpenScreenMcpServer` registers them. Both servers serve the same six, from the same code. Their state (the take running, the export running, each take's start time, each project's last export) lives in what `createMediaTools` returns, so the in-app server, which builds a fresh `McpServer` per request, keeps it across requests and across a restart of its port. They share the runner the document tools use: the app's one runner in the app, the routed one of `stdio-server.ts` over stdio, so their document calls go to the app while it runs.++What differs between the two servers is who records, handed in as a `TakeRecorder`:++| | In-app server | `openscreen mcp` |+|---|---|---|+| Recorder | `createAppRecorder` (app-recorder.ts) | `runnerRecorder` (media-tools.ts) |+| `startRecording` | Points the recording bar at the request, as the editor's Record mode does before it hands over: the source, picked from the list `listSources` shows (`pickRecordingSource`, as `openscreen record`), and the microphone, system audio and editable cursor in the recording prefs. Then hands over as the editor's Record button does (`start-new-recording`): the editor closes, the HUD starts the take with its countdown and its camera setting. Returns once `set-recording-state` says it records. Refused while the editor has unsaved changes, since the editor closes. Where the system's picker owns the choice (the Linux portal, Apple's picker on macOS 15.2+), the request picks nothing: that picker asks the user. | A hidden `cli-record` runner of its own process, as `openscreen record`. |+| `stopRecording` | Presses the HUD's Stop, as the tray does. The HUD saves the take and hands it to the editor (`set-current-recording-session`), which imports it as for any take: one clip, measured, and the zooms on its clicks when Record mode's *Auto-zoom after recording* is on. The recorder waits for the editor's document to hold the take with its real length, then for its revision to hold still for 1.5 s, and returns that project, open in the editor. A `title` is applied through the editor. | Stops the runner and makes the project here (`createProjectFromVideo`): a fresh id no editor can hold, the zooms planned from the clicks. |+| The user's settings | The source, microphone, system audio and cursor mode the user had come back once the take is captured. | Untouched: the runner never saves them. |-`registerMediaTools` adds the tools that make a video around the edits. They share the runner the document tools use, the routed one of `stdio-server.ts`, so their document calls go to the app while it runs:+Then both servers carry on alike:-- `stopRecording` turns the take into a project and creates its checkpoint through the runner. The new project itself is written by the CLI process: a fresh id no editor can hold.-- `setPointerTrack` gives a script-driven take a pointer track and plans zooms on its clicks. `pointerTrackEdit` computes the new sidecar and the zooms from the project the runner read, writes nothing itself, and hands both to the runner as a `RunnerEdit`. The runner then applies the same refusals as any edit (another process's editor, no checkpoint, a project changed mid-call) before writing anything, saves the project, and only then writes the sidecar, keeping its previous content for the checkpoints. Every refusal comes back as the tool's own text result. A sidecar write that fails after the save is reported as a partial edit: the project was saved, the pointer track was not. A `RunnerEdit` is a closure and cannot be forwarded, so the call carries what the edit needs (`events`, and `takes`, each take's start time by video): the app's channel serves `setPointerTrack` with those args and runs `pointerTrackEdit` in its own runner.-- `exportVideo` and `getFrames` read projects; they write none.+- `stopRecording` creates the take's checkpoint through the runner, and records when the take started, by its video, for `setPointerTrack`.+- `setPointerTrack` gives a script-driven take a pointer track and plans zooms on its clicks. `pointerTrackEdit` computes the new sidecar and the zooms from the project the runner read, writes nothing itself, and hands both to the runner as a `RunnerEdit`. The runner then applies the same refusals as any edit (another process's editor, no checkpoint, a project changed mid-call) before writing anything, saves the project, and only then writes the sidecar, keeping its previous content for the checkpoints. Every refusal comes back as the tool's own text result. A sidecar write that fails after the save is reported as a partial edit: the project was saved, the pointer track was not. A `RunnerEdit` is a closure and cannot be forwarded, so the call carries what the edit needs (`events`, and `takes`, each take's start time by video): the app's channel serves `setPointerTrack` with those args and runs `pointerTrackEdit` in its own runner. That is the channel's own registration, not the in-app server's tool: the takes of `openscreen mcp` are known to it alone.+- `exportVideo` renders in a hidden `cli-export` runner, the same in both processes: in the app, `listSources` and `exportVideo` run the CLI's runners (`createRunnerHost` with `createRunnerWindow`), whose IPC the app registers on first use. The runner reads the project by id (`CliExportRequest.projectId`, the editor's own `aiEdition.get`), not by path: opening a file by path moves the main process's current project and recording-session slot, which in the app is the hand-off from the recorder to the editor.+- `exportVideo` and `getFrames` read projects; they write none. Over HTTP their paths must be absolute.## `openscreen mcp` and the running app@@ -135,7 +151,7 @@ The stdio server (`openscreen mcp`, [`stdio-server.ts`](../../electron/mcp/stdio**In-app server (HTTP)**-- Streamable HTTP, **stateless**: a fresh `McpServer` + transport per request, the SDK's documented shape for a server that keeps no session state. The runner, and so the checkpoints, live as long as the running server.+- Streamable HTTP, **stateless**: a fresh `McpServer` + transport per request, the SDK's documented shape for a server that keeps no session state. The runner, and so the checkpoints, and the media tools' state live as long as the app.- Bound to `127.0.0.1` only, endpoint `/mcp`, default port 47821 (configurable, 1024–65535).- Every request needs `Authorization: Bearer <token>`, compared in constant time. The token is 32 random bytes, stored with `safeStorage`, and read only once the server is enabled, so users who never enable it never meet a Keychain prompt for it. Regenerating it restarts the server, so the old one stops working at once.- The `Host` must be `127.0.0.1:<port>` or `localhost:<port>`, and a request carrying any other `Origin` is refused — this blocks a web page from reaching the server through DNS rebinding.@@ -147,7 +163,7 @@ The stdio server (`openscreen mcp`, [`stdio-server.ts`](../../electron/mcp/stdio## Lifecycle-`registerIpcHandlers` builds the `McpController` (it is where the agent's own dependencies — the cursor reader, the LLM config — live) and returns it; **`main.ts` starts it**. The headless CLI shares `registerIpcHandlers` and must never bind the port a running app is listening on, and a bench run has no use for it, so neither calls `startIfEnabled`. `main.ts` also opens the channel for `openscreen mcp` (`serveAppChannel`), always, and closes it on `will-quit`. `openscreen mcp` reuses the same dependencies (`mcpToolDeps`) with `transport: "stdio"` and edits always allowed.+`registerIpcHandlers` builds the `McpController` and the in-app media tools with their recorder (it is where the agent's own dependencies — the cursor reader, the LLM config — live, and the recording handlers the recorder listens to) and returns it; **`main.ts` starts it**, and hands `registerIpcHandlers` the editor's unsaved-changes flag that `startRecording` checks. The headless CLI shares `registerIpcHandlers` and must never bind the port a running app is listening on, and a bench run has no use for it, so neither calls `startIfEnabled`. `main.ts` also opens the channel for `openscreen mcp` (`serveAppChannel`), always, and closes it on `will-quit`. `openscreen mcp` reuses the same dependencies (`mcpToolDeps`) with `transport: "stdio"` and edits always allowed.## Connecting a client@@ -169,7 +185,8 @@ codex mcp add openscreen -- "<executable>" mcp## Known gaps-- **The in-app server cannot record or export.** `openscreen mcp` now covers the whole loop, editing the open project through the app; the in-app server gets the media tools later in #1174.+- **`openscreen mcp` records in its own process, app or no app.** Only its document calls are forwarded; its takes, exports and frames stay in the CLI process, and its take lands in the project list rather than in the editor. The in-app server is the way to record through the app's recording bar.+- **An in-app take is ready by a quiet period.** The editor lays a take out in several saves and says none of them is the last: the recorder waits for its revision to hold for 1.5 s. A save later than that (a slow auto-zoom pass) lands after the checkpoint, so `restoreCheckpoint` takes it back with the client's edits.- **No Ctrl+Z for edits to closed projects.** Their undo is the checkpoint the write requires, which lives in memory: it is gone once its server goes away or 20 newer ones push it out, and the edits stay.- **An editor that stops answering looks closed.** A snapshot unanswered for 30 s reads as "no project open", so an edit naming the project that editor holds would go to its file, and the editor's next save would drop it. It takes a renderer hung for 30 s.-- **No project management.** Projects can be listed, read and edited, and `openscreen mcp` creates one per take; none can be renamed or deleted, and nothing imports media.+- **No project management.** Projects can be listed, read and edited, and each take makes one; only a take's `title` names it, none can be renamed or deleted afterwards, and nothing imports media.diff --git a/technical-documentation/testing/manual-e2e-checklist.md b/technical-documentation/testing/manual-e2e-checklist.mdindex 980a3adc5..ccb79b010 100644--- a/technical-documentation/testing/manual-e2e-checklist.md+++ b/technical-documentation/testing/manual-e2e-checklist.md@@ -570,10 +570,11 @@ The agent may only call the fixed tool set in [ai-agent.md](../architecture/ai-a## MCP server — post-2.0.0-Two servers. The **in-app** one is HTTP, in *AI settings* → *MCP server*, off by default. The **stdio** one is the installed executable started by the agent itself: `claude mcp add openscreen -- "<exe>" mcp`, with `<exe>` `%LOCALAPPDATA%\Programs\Openscreen\Openscreen.exe` on Windows or `/Applications/Openscreen.app/Contents/MacOS/Openscreen` on macOS. Only stdio records, exports and reads frames. Drive these checks from a real MCP client against the installed build, never with a hand-written JSON request.+Two servers. The **in-app** one is HTTP, in *AI settings* → *MCP server*, off by default. The **stdio** one is the installed executable started by the agent itself: `claude mcp add openscreen -- "<exe>" mcp`, with `<exe>` `%LOCALAPPDATA%\Programs\Openscreen\Openscreen.exe` on Windows or `/Applications/Openscreen.app/Contents/MacOS/Openscreen` on macOS. Both serve the same tools, recording, export and frames included (#1174). Drive these checks from a real MCP client against the installed build, never with a hand-written JSON request.-- [ ] In *AI settings*, confirm *Enable MCP server* and *Allow MCP clients to edit your projects* are off by default; enable the server and confirm the status reads *Running* with a *Port*, an *Access token* (Show, Copy, Regenerate) and the Claude Code and Codex snippets. Change the port, *Apply*, and confirm a client reconnects on it.-- [ ] With edits not allowed, confirm an edit tool is refused; allow them and confirm the edit lands in the open editor and undoes with `Ctrl/Cmd+Z`.+- [ ] In *AI settings*, confirm *Enable MCP server* and *Allow MCP clients to edit your projects, record and export* are off by default; enable the server and confirm the status reads *Running* with a *Port*, an *Access token* (Show, Copy, Regenerate) and the Claude Code and Codex snippets. Change the port, *Apply*, and confirm a client reconnects on it.+- [ ] With edits not allowed, confirm an edit tool, `startRecording` and `exportVideo` are refused, naming *MCP edits*; allow them and confirm the edit lands in the open editor and undoes with `Ctrl/Cmd+Z`.+- [ ] From a client of the **in-app** server, `startRecording` on a window: the editor closes and the recording bar records, its countdown first, with no second recorder process. Click in the window, `stopRecording`: the editor opens on the take, laid out and zoomed as after a take started by hand, and the returned `projectId` is that project. An edit to it lands live and undoes with `Ctrl/Cmd+Z`; `exportVideo` to an absolute path and `getFrames` on it work. Confirm the recording bar's microphone and system audio are back to what they were before the take, and that `startRecording` is refused while the editor has unsaved changes.- [ ] Confirm `"<exe>" help` lists `mcp`, register the stdio server in an MCP client, and confirm `listSources` lists displays, windows and microphones.- [ ] Run `startRecording` on a window, click inside it a few times, `stopRecording`, and confirm the returned project is in the editor's project list with one clip and the zooms its `autoZooms` count announces. Clicks close in time (3 s or less) and on screen share one zoom, and a click in the first seconds or the stopping click gets none, so there can be fewer zooms than clicks. On macOS 15.2+, confirm Apple's picker never appears; on Linux, confirm the portal asks.- [ ] Edit that project while it is closed, `restoreCheckpoint` with the returned checkpoint, and confirm the project is back to the raw take. Confirm an edit to a closed project with no checkpoint is refused.diff --git a/website/docs/ai-editing.md b/website/docs/ai-editing.mdindex d30acc0b0..4015709a8 100644--- a/website/docs/ai-editing.md+++ b/website/docs/ai-editing.md@@ -67,7 +67,7 @@ If you already use an AI coding agent such as Claude Code or Codex, it can drive2. Copy the **Claude Code** or **Codex** command shown there and run it in a terminal. The Claude Code command carries the access token. Codex reads it from the `OPENSCREEN_MCP_TOKEN` environment variable instead: set that in the shell you start Codex from.3. Ask your agent for the edit, on the project open in the OpenScreen editor or on any other project in your list.-The tools are the ones the built-in agent uses. They act on the project open in the editor unless the client names another one: it can list every project and read or edit any of them. MCP clients can only **read** until you also turn on **MCP edits** in the MCP server section; this switch is separate from the built-in agent's **Agent edits**, and it starts off. Once on, each edit is saved as it lands:+The tools are the ones the built-in agent uses, plus the ones that record, export and look at a video ([below](#letting-an-agent-make-the-whole-video)). They act on the project open in the editor unless the client names another one: it can list every project and read or edit any of them. MCP clients can only **read** until you also turn on **MCP edits** in the MCP server section: until then every edit, recording and export they try is refused. This switch is separate from the built-in agent's **Agent edits**, and it starts off. Once on, each edit is saved as it lands:- **On the project open in the editor**, an edit is undone with `Ctrl/Cmd + Z`. Clients are told to save a checkpoint before a series of edits, so you can ask them to put the project back as it was in a single step, which `Ctrl/Cmd + Z` can itself undo.- **On any other project**, an edit is saved to its file, where `Ctrl/Cmd + Z` cannot reach it. A client must save a checkpoint of that project before its first edit, and putting the project back from it is the only undo.@@ -76,9 +76,11 @@ Checkpoints are kept in OpenScreen's memory: they are lost when it quits or when## Letting an agent make the whole video-The server above edits projects. To have an agent make a whole video on its own, from the recording to the export, add OpenScreen to it as a stdio server instead: the agent starts the app's own executable with `mcp`. It gets the same editing tools, plus `listSources`, `startRecording`, `stopRecording`, `setPointerTrack`, `exportVideo` and `getFrames`.+An agent can make a whole video on its own, from the recording to the export. Besides the editing tools, both ways of adding OpenScreen to it give it `listSources`, `startRecording`, `stopRecording`, `setPointerTrack`, `exportVideo` and `getFrames`.-The quickest way is to paste this into Claude Code:+**Through the server above**, a take is recorded by OpenScreen itself, as with its Record button: the editor closes, the recording bar counts down and records, and the take opens in the editor as a new project, where you watch each edit land. It needs **MCP edits** on, and the recording bar gets your own settings back once the take ends.++**As a stdio server**, it needs no setting at all: the agent starts the app's own executable with `mcp`. The quickest way is to paste this into Claude Code:```textInstall the OpenScreen demo skill with `npx skills add getopenscreen/openscreen --skill openscreen-demo -a claude-code`, then follow it to make a demo video of this feature.diff --git a/website/i18n/de/docusaurus-plugin-content-docs/current/ai-editing.md b/website/i18n/de/docusaurus-plugin-content-docs/current/ai-editing.mdindex 1002aa56e..3c700938d 100644--- a/website/i18n/de/docusaurus-plugin-content-docs/current/ai-editing.md+++ b/website/i18n/de/docusaurus-plugin-content-docs/current/ai-editing.md@@ -67,7 +67,7 @@ Wenn du bereits einen KI-Coding-Agenten wie Claude Code oder Codex nutzt, kann e2. Kopiere den dort angezeigten Befehl für **Claude Code** oder **Codex** und führe ihn in einem Terminal aus. Der Befehl für Claude Code enthält das Zugriffstoken. Codex liest es stattdessen aus der Umgebungsvariable `OPENSCREEN_MCP_TOKEN`: Setze sie in der Shell, aus der du Codex startest.3. Bitte deinen Agenten um die Änderung, am im OpenScreen-Editor geöffneten Projekt oder an einem beliebigen anderen Projekt deiner Liste.-Die Werkzeuge sind die, die der eingebaute Agent nutzt. Sie wirken auf das im Editor geöffnete Projekt, es sei denn, der Client nennt ein anderes: Er kann alle Projekte auflisten und jedes davon lesen oder bearbeiten. MCP-Clients können nur **lesen**, bis du im Abschnitt MCP-Server auch **MCP-Änderungen** einschaltest; dieser Schalter ist von **Agenten-Änderungen**, dem des eingebauten Agenten, getrennt und steht anfangs auf aus. Ist er an, wird jede Änderung gespeichert, sobald sie ankommt:+Die Werkzeuge sind die, die der eingebaute Agent nutzt, dazu die, die ein Video aufnehmen, exportieren und ansehen ([unten](#letting-an-agent-make-the-whole-video)). Sie wirken auf das im Editor geöffnete Projekt, es sei denn, der Client nennt ein anderes: Er kann alle Projekte auflisten und jedes davon lesen oder bearbeiten. MCP-Clients können nur **lesen**, bis du im Abschnitt MCP-Server auch **MCP-Änderungen** einschaltest: Bis dahin wird jede Bearbeitung, Aufnahme oder jeder Export, den sie versuchen, abgelehnt. Dieser Schalter ist von **Agenten-Änderungen**, dem des eingebauten Agenten, getrennt und steht anfangs auf aus. Ist er an, wird jede Änderung gespeichert, sobald sie ankommt:- **Am im Editor geöffneten Projekt** wird eine Änderung mit `Ctrl/Cmd + Z` rückgängig gemacht. Clients werden angewiesen, vor einer Reihe von Änderungen einen Wiederherstellungspunkt zu speichern. So kannst du sie bitten, das Projekt in einem einzigen Schritt wiederherzustellen, wie es war, und auch diesen Schritt kann `Ctrl/Cmd + Z` rückgängig machen.- **An jedem anderen Projekt** wird eine Änderung in seiner Datei gespeichert, wo `Ctrl/Cmd + Z` sie nicht erreicht. Ein Client muss vor der ersten Änderung einen Wiederherstellungspunkt dieses Projekts speichern, und dorthin zurückzukehren ist der einzige Weg, sie rückgängig zu machen.@@ -76,7 +76,11 @@ Wiederherstellungspunkte liegen im Speicher von OpenScreen: Sie gehen verloren,## Einen Agenten das ganze Video erstellen lassen {#letting-an-agent-make-the-whole-video}-Der Server oben bearbeitet Projekte. Soll ein Agent ein ganzes Video selbstständig erstellen, von der Aufnahme bis zum Export, füge OpenScreen stattdessen als stdio-Server zum Agenten hinzu: Der Agent startet die eigene ausführbare Datei der App mit `mcp`. Er bekommt dieselben Bearbeitungswerkzeuge, dazu `listSources`, `startRecording`, `stopRecording`, `setPointerTrack`, `exportVideo` und `getFrames`.+Ein Agent kann ein ganzes Video selbstständig erstellen, von der Aufnahme bis zum Export. Neben den Bearbeitungswerkzeugen geben ihm beide Wege, OpenScreen hinzuzufügen, `listSources`, `startRecording`, `stopRecording`, `setPointerTrack`, `exportVideo` und `getFrames`.++**Über den Server oben** nimmt OpenScreen eine Aufnahme selbst auf, wie mit seinem Aufnahme-Button: Der Editor schließt sich, die Aufnahmeleiste zählt herunter und nimmt auf, und die Aufnahme öffnet sich im Editor als neues Projekt, wo du jede Änderung ankommen siehst. Dafür muss **MCP-Änderungen** an sein, und die Aufnahmeleiste bekommt am Ende der Aufnahme deine eigenen Einstellungen zurück.++**Als stdio-Server** braucht es gar keine Einstellung: Der Agent startet die eigene ausführbare Datei der App mit `mcp`.Am schnellsten fügst du Folgendes in Claude Code ein:diff --git a/website/i18n/es/docusaurus-plugin-content-docs/current/ai-editing.md b/website/i18n/es/docusaurus-plugin-content-docs/current/ai-editing.mdindex 41d3cf334..ed57e68ed 100644--- a/website/i18n/es/docusaurus-plugin-content-docs/current/ai-editing.md+++ b/website/i18n/es/docusaurus-plugin-content-docs/current/ai-editing.md@@ -67,7 +67,7 @@ Si ya usas un agente de código con IA como Claude Code o Codex, puede manejar l2. Copia el comando de **Claude Code** o de **Codex** que aparece ahí y ejecútalo en una terminal. El comando de Claude Code lleva el token de acceso. Codex, en cambio, lo lee de la variable de entorno `OPENSCREEN_MCP_TOKEN`: defínela en el shell desde el que inicias Codex.3. Pídele la edición a tu agente, sobre el proyecto abierto en el editor de OpenScreen o sobre cualquier otro proyecto de tu lista.-Las herramientas son las que usa el agente integrado. Actúan sobre el proyecto abierto en el editor, salvo que el cliente indique otro: puede listar todos los proyectos y leer o editar cualquiera de ellos. Los clientes MCP solo pueden **leer** hasta que también actives **Ediciones por MCP** en la sección Servidor MCP; este interruptor es independiente de **Ediciones del agente**, el del agente integrado, y empieza desactivado. Una vez activado, cada edición se guarda en cuanto se aplica:+Las herramientas son las que usa el agente integrado, además de las que graban, exportan y miran un video ([más abajo](#letting-an-agent-make-the-whole-video)). Actúan sobre el proyecto abierto en el editor, salvo que el cliente indique otro: puede listar todos los proyectos y leer o editar cualquiera de ellos. Los clientes MCP solo pueden **leer** hasta que también actives **Ediciones por MCP** en la sección Servidor MCP: hasta entonces se rechaza cada edición, grabación o exportación que intenten. Este interruptor es independiente de **Ediciones del agente**, el del agente integrado, y empieza desactivado. Una vez activado, cada edición se guarda en cuanto se aplica:- **En el proyecto abierto en el editor**, una edición se deshace con `Ctrl/Cmd + Z`. A los clientes se les indica que guarden un punto de restauración antes de una serie de ediciones, así que puedes pedirles que dejen el proyecto como estaba en un solo paso, que el propio `Ctrl/Cmd + Z` puede deshacer.- **En cualquier otro proyecto**, una edición se guarda en su archivo, fuera del alcance de `Ctrl/Cmd + Z`. Un cliente debe guardar un punto de restauración de ese proyecto antes de su primera edición, y volver a él es la única forma de deshacerla.@@ -76,7 +76,11 @@ Los puntos de restauración se guardan en la memoria de OpenScreen: se pierden c## Dejar que un agente haga todo el video {#letting-an-agent-make-the-whole-video}-El servidor de arriba edita proyectos. Para que un agente haga un video completo por sí solo, desde la grabación hasta la exportación, agrega en cambio OpenScreen al agente como servidor stdio: el agente inicia el propio ejecutable de la app con `mcp`. Obtiene las mismas herramientas de edición, además de `listSources`, `startRecording`, `stopRecording`, `setPointerTrack`, `exportVideo` y `getFrames`.+Un agente puede hacer un video completo por sí solo, desde la grabación hasta la exportación. Además de las herramientas de edición, las dos formas de agregar OpenScreen al agente le dan `listSources`, `startRecording`, `stopRecording`, `setPointerTrack`, `exportVideo` y `getFrames`.++**Con el servidor de arriba**, la toma la graba el propio OpenScreen, como con su botón Grabar: el editor se cierra, la barra de grabación hace su cuenta regresiva y graba, y la toma se abre en el editor como un proyecto nuevo, donde ves llegar cada edición. Necesita **Ediciones por MCP** activado, y la barra de grabación recupera tus propios ajustes al terminar la toma.++**Como servidor stdio**, no necesita ningún ajuste: el agente inicia el propio ejecutable de la app con `mcp`.La forma más rápida es pegar esto en Claude Code:diff --git a/website/i18n/fr/docusaurus-plugin-content-docs/current/ai-editing.md b/website/i18n/fr/docusaurus-plugin-content-docs/current/ai-editing.mdindex d0eebb869..0c1cfa146 100644--- a/website/i18n/fr/docusaurus-plugin-content-docs/current/ai-editing.md+++ b/website/i18n/fr/docusaurus-plugin-content-docs/current/ai-editing.md@@ -67,7 +67,7 @@ Si vous utilisez déjà un agent de code IA comme Claude Code ou Codex, il peut2. Copiez la commande **Claude Code** ou **Codex** affichée à cet endroit et lancez-la dans un terminal. La commande Claude Code contient le jeton d'accès. Codex, lui, le lit dans la variable d'environnement `OPENSCREEN_MCP_TOKEN` : définissez-la dans le shell depuis lequel vous lancez Codex.3. Demandez la modification à votre agent, sur le projet ouvert dans l'éditeur d'OpenScreen ou sur n'importe quel autre projet de votre liste.-Les outils sont ceux qu'utilise l'agent intégré. Ils agissent sur le projet ouvert dans l'éditeur, sauf si le client en désigne un autre : il peut lister tous les projets et lire ou modifier n'importe lequel. Les clients MCP ne peuvent que **lire** tant que vous n'avez pas aussi activé **Modifications par MCP** dans la section Serveur MCP ; cet interrupteur est distinct de **Modifications par l'agent**, celui de l'agent intégré, et il est désactivé au départ. Une fois activé, chaque modification est enregistrée dès qu'elle est appliquée :+Les outils sont ceux qu'utilise l'agent intégré, plus ceux qui enregistrent, exportent et regardent une vidéo ([plus bas](#letting-an-agent-make-the-whole-video)). Ils agissent sur le projet ouvert dans l'éditeur, sauf si le client en désigne un autre : il peut lister tous les projets et lire ou modifier n'importe lequel. Les clients MCP ne peuvent que **lire** tant que vous n'avez pas aussi activé **Modifications par MCP** dans la section Serveur MCP : jusque-là, chaque modification, enregistrement ou export qu'ils tentent est refusé. Cet interrupteur est distinct de **Modifications par l'agent**, celui de l'agent intégré, et il est désactivé au départ. Une fois activé, chaque modification est enregistrée dès qu'elle est appliquée :- **Sur le projet ouvert dans l'éditeur**, une modification s'annule avec `Ctrl/Cmd + Z`. Les clients ont pour consigne d'enregistrer un point de restauration avant une série de modifications : vous pouvez donc leur demander de remettre le projet dans son état d'avant en une seule étape, que `Ctrl/Cmd + Z` peut lui-même annuler.- **Sur tout autre projet**, une modification est enregistrée dans son fichier, hors de portée de `Ctrl/Cmd + Z`. Un client doit enregistrer un point de restauration de ce projet avant sa première modification, et y revenir est la seule façon de l'annuler.@@ -76,7 +76,11 @@ Les points de restauration sont gardés dans la mémoire d'OpenScreen : ils son## Laisser un agent faire toute la vidéo {#letting-an-agent-make-the-whole-video}-Le serveur ci-dessus modifie des projets. Pour qu'un agent fasse une vidéo entière tout seul, de l'enregistrement à l'export, ajoutez plutôt OpenScreen à l'agent comme serveur stdio : l'agent lance l'exécutable même de l'application avec `mcp`. Il dispose des mêmes outils d'édition, plus `listSources`, `startRecording`, `stopRecording`, `setPointerTrack`, `exportVideo` et `getFrames`.+Un agent peut faire une vidéo entière tout seul, de l'enregistrement à l'export. En plus des outils d'édition, les deux façons d'ajouter OpenScreen à l'agent lui donnent `listSources`, `startRecording`, `stopRecording`, `setPointerTrack`, `exportVideo` et `getFrames`.++**Par le serveur ci-dessus**, une prise est enregistrée par OpenScreen lui-même, comme avec son bouton Enregistrer : l'éditeur se ferme, la barre d'enregistrement fait son décompte et enregistre, et la prise s'ouvre dans l'éditeur comme nouveau projet, où vous voyez chaque modification arriver. Il faut que **Modifications par MCP** soit activé, et la barre d'enregistrement retrouve vos propres réglages à la fin de la prise.++**Comme serveur stdio**, aucun réglage n'est nécessaire : l'agent lance l'exécutable même de l'application avec `mcp`.Le plus rapide est de coller ceci dans Claude Code :diff --git a/website/i18n/ja/docusaurus-plugin-content-docs/current/ai-editing.md b/website/i18n/ja/docusaurus-plugin-content-docs/current/ai-editing.mdindex 30e0fb684..d2be7ea54 100644--- a/website/i18n/ja/docusaurus-plugin-content-docs/current/ai-editing.md+++ b/website/i18n/ja/docusaurus-plugin-content-docs/current/ai-editing.md@@ -67,7 +67,7 @@ Claude Code や Codex などの AI コーディングエージェントをすで2. そこに表示される **Claude Code** または **Codex** のコマンドをコピーし、ターミナルで実行します。Claude Code のコマンドにはアクセストークンが含まれています。Codex は代わりに環境変数 `OPENSCREEN_MCP_TOKEN` からトークンを読み取るため、Codex を起動するシェルでこの変数を設定してください。3. OpenScreen のエディターで開いているプロジェクト、または一覧にあるほかのプロジェクトについて、エージェントに編集を依頼します。-ツールは組み込みのエージェントが使うものと同じです。クライアントが別のプロジェクトを指定しない限り、エディターで開いているプロジェクトに作用します。クライアントはすべてのプロジェクトを一覧でき、どれでも読み取りや編集ができます。MCP サーバーのセクションで**MCP による編集**もオンにするまで、MCP クライアントは**読み取る**ことしかできません。このスイッチは組み込みのエージェントの**エージェントによる編集**とは別で、最初はオフです。オンにすると、各編集は反映された時点で保存されます。+ツールは組み込みのエージェントが使うものと同じで、さらに動画を録画、エクスポートし、確認するツールがあります([後述](#letting-an-agent-make-the-whole-video))。クライアントが別のプロジェクトを指定しない限り、エディターで開いているプロジェクトに作用します。クライアントはすべてのプロジェクトを一覧でき、どれでも読み取りや編集ができます。MCP サーバーのセクションで**MCP による編集**もオンにするまで、MCP クライアントは**読み取る**ことしかできず、編集、録画、エクスポートはすべて拒否されます。このスイッチは組み込みのエージェントの**エージェントによる編集**とは別で、最初はオフです。オンにすると、各編集は反映された時点で保存されます。- **エディターで開いているプロジェクト**では、編集は `Ctrl/Cmd + Z` で元に戻せます。クライアントには一連の編集の前にチェックポイントを保存するよう指示されているため、プロジェクトを 1 回の操作で元の状態に戻すよう頼むことができ、その操作自体も `Ctrl/Cmd + Z` で取り消せます。- **それ以外のプロジェクト**では、編集はそのファイルに保存され、`Ctrl/Cmd + Z` では元に戻せません。クライアントは最初の編集の前にそのプロジェクトのチェックポイントを保存する必要があり、そこへ戻すことが唯一の取り消し方法です。@@ -76,7 +76,11 @@ Claude Code や Codex などの AI コーディングエージェントをすで## エージェントに動画全体を作らせる {#letting-an-agent-make-the-whole-video}-上のサーバーはプロジェクトを編集するものです。録画からエクスポートまで、エージェントに動画全体を自力で作らせるには、代わりに OpenScreen を stdio サーバーとしてエージェントに追加します。エージェントは、アプリ自身の実行ファイルを `mcp` 付きで起動します。エージェントは同じ編集ツールに加えて、`listSources`、`startRecording`、`stopRecording`、`setPointerTrack`、`exportVideo`、`getFrames` を使えます。+エージェントは、録画からエクスポートまで、動画全体を自力で作れます。どちらの方法で OpenScreen を追加しても、編集ツールに加えて `listSources`、`startRecording`、`stopRecording`、`setPointerTrack`、`exportVideo`、`getFrames` を使えます。++**上のサーバーを使う場合**、録画は OpenScreen 自身が、録画ボタンを押したときと同じように行います。エディターが閉じ、録画バーがカウントダウンして録画し、録画は新しいプロジェクトとしてエディターで開きます。そこで各編集が反映されるのを確認できます。**MCP による編集**をオンにする必要があり、録画が終わると録画バーの設定はあなた自身のものに戻ります。++**stdio サーバーとして追加する場合**、設定は一切不要です。エージェントは、アプリ自身の実行ファイルを `mcp` 付きで起動します。いちばん手早いのは、次の内容を Claude Code に貼り付けることです。diff --git a/website/i18n/pt-BR/docusaurus-plugin-content-docs/current/ai-editing.md b/website/i18n/pt-BR/docusaurus-plugin-content-docs/current/ai-editing.mdindex 03fd609a8..22086702a 100644--- a/website/i18n/pt-BR/docusaurus-plugin-content-docs/current/ai-editing.md+++ b/website/i18n/pt-BR/docusaurus-plugin-content-docs/current/ai-editing.md@@ -67,7 +67,7 @@ Se você já usa um agente de código com IA, como o Claude Code ou o Codex, ele2. Copie o comando do **Claude Code** ou do **Codex** exibido ali e execute-o em um terminal. O comando do Claude Code leva o token de acesso. Já o Codex o lê da variável de ambiente `OPENSCREEN_MCP_TOKEN`: defina-a no shell a partir do qual você inicia o Codex.3. Peça a edição ao seu agente, no projeto aberto no editor do OpenScreen ou em qualquer outro projeto da sua lista.-As ferramentas são as que o agente integrado usa. Elas agem sobre o projeto aberto no editor, a menos que o cliente indique outro: ele pode listar todos os projetos e ler ou editar qualquer um deles. Os clientes MCP só podem **ler** até você também ativar **Edições via MCP** na seção Servidor MCP; esse interruptor é separado de **Edições do agente**, o do agente integrado, e começa desativado. Depois de ativado, cada edição é salva assim que é aplicada:+As ferramentas são as que o agente integrado usa, mais as que gravam, exportam e olham um vídeo ([mais abaixo](#letting-an-agent-make-the-whole-video)). Elas agem sobre o projeto aberto no editor, a menos que o cliente indique outro: ele pode listar todos os projetos e ler ou editar qualquer um deles. Os clientes MCP só podem **ler** até você também ativar **Edições via MCP** na seção Servidor MCP: até lá, toda edição, gravação ou exportação que tentarem é recusada. Esse interruptor é separado de **Edições do agente**, o do agente integrado, e começa desativado. Depois de ativado, cada edição é salva assim que é aplicada:- **No projeto aberto no editor**, uma edição se desfaz com `Ctrl/Cmd + Z`. Os clientes são instruídos a salvar um ponto de restauração antes de uma série de edições, então você pode pedir a eles que deixem o projeto como estava em um único passo, que o próprio `Ctrl/Cmd + Z` pode desfazer.- **Em qualquer outro projeto**, uma edição é salva no arquivo dele, fora do alcance de `Ctrl/Cmd + Z`. Um cliente precisa salvar um ponto de restauração desse projeto antes da primeira edição, e voltar a ele é a única forma de desfazê-la.@@ -76,7 +76,11 @@ Os pontos de restauração ficam na memória do OpenScreen: eles se perdem quand## Como deixar um agente fazer o vídeo inteiro {#letting-an-agent-make-the-whole-video}-O servidor acima edita projetos. Para que um agente faça um vídeo inteiro sozinho, da gravação à exportação, adicione, em vez disso, o OpenScreen ao agente como servidor stdio: o agente inicia o próprio executável do app com `mcp`. Ele recebe as mesmas ferramentas de edição, mais `listSources`, `startRecording`, `stopRecording`, `setPointerTrack`, `exportVideo` e `getFrames`.+Um agente pode fazer um vídeo inteiro sozinho, da gravação à exportação. Além das ferramentas de edição, as duas formas de adicionar o OpenScreen ao agente lhe dão `listSources`, `startRecording`, `stopRecording`, `setPointerTrack`, `exportVideo` e `getFrames`.++**Pelo servidor acima**, a gravação é feita pelo próprio OpenScreen, como com o botão Gravar: o editor fecha, a barra de gravação faz a contagem regressiva e grava, e a gravação abre no editor como um novo projeto, onde você vê cada edição chegar. É preciso ativar **Edições via MCP**, e a barra de gravação volta às suas próprias configurações quando a gravação termina.++**Como servidor stdio**, não é preciso nenhuma configuração: o agente inicia o próprio executável do app com `mcp`.O jeito mais rápido é colar isto no Claude Code:diff --git a/website/i18n/zh-CN/docusaurus-plugin-content-docs/current/ai-editing.md b/website/i18n/zh-CN/docusaurus-plugin-content-docs/current/ai-editing.mdindex 40c882244..2a110245d 100644--- a/website/i18n/zh-CN/docusaurus-plugin-content-docs/current/ai-editing.md+++ b/website/i18n/zh-CN/docusaurus-plugin-content-docs/current/ai-editing.md@@ -67,7 +67,7 @@ ChatGPT 和 GitHub Copilot 登录选项已**在 1.8.0 中移除**。它们的工2. 复制那里显示的 **Claude Code** 或 **Codex** 命令,并在终端中运行。Claude Code 命令中带有访问令牌。Codex 则改为从 `OPENSCREEN_MCP_TOKEN` 环境变量读取令牌:请在启动 Codex 的终端中设置它。3. 让你的 AI 代理进行编辑,对象可以是 OpenScreen 编辑器中打开的项目,也可以是你列表中的任何其他项目。-这些工具就是内置 AI 代理所使用的工具。除非客户端指定其他项目,它们作用于编辑器中打开的项目:客户端可以列出所有项目,并读取或编辑其中任何一个。在你同时开启 MCP 服务器部分中的**MCP 编辑**之前,MCP 客户端只能**读取**;这个开关独立于内置 AI 代理的**智能体编辑**开关,默认处于关闭状态。开启后,每项编辑都会在生效时立即保存:+这些工具就是内置 AI 代理所使用的工具,另外还有录制、导出和查看视频的工具([见下文](#letting-an-agent-make-the-whole-video))。除非客户端指定其他项目,它们作用于编辑器中打开的项目:客户端可以列出所有项目,并读取或编辑其中任何一个。在你同时开启 MCP 服务器部分中的**MCP 编辑**之前,MCP 客户端只能**读取**,它们尝试的每项编辑、录制或导出都会被拒绝。这个开关独立于内置 AI 代理的**智能体编辑**开关,默认处于关闭状态。开启后,每项编辑都会在生效时立即保存:- **对编辑器中打开的项目**,编辑可用 `Ctrl/Cmd + Z` 撤销。客户端会被要求在进行一系列编辑之前保存一个检查点,因此你可以让它们一步把项目恢复原样,而这一步本身也可以用 `Ctrl/Cmd + Z` 撤销。- **对其他任何项目**,编辑会保存到它的文件中,`Ctrl/Cmd + Z` 无法撤销。客户端必须在第一次编辑之前保存该项目的检查点,恢复到这个检查点是唯一的撤销方式。@@ -76,7 +76,11 @@ ChatGPT 和 GitHub Copilot 登录选项已**在 1.8.0 中移除**。它们的工## 让 AI 代理制作整段视频 {#letting-an-agent-make-the-whole-video}-上面的服务器用于编辑项目。若要让 AI 代理从录制到导出独立完成一整段视频,请改为把 OpenScreen 作为 stdio 服务器添加到 AI 代理中:AI 代理会用 `mcp` 启动应用自身的可执行文件。它能使用同样的编辑工具,另外还有 `listSources`、`startRecording`、`stopRecording`、`setPointerTrack`、`exportVideo` 和 `getFrames`。+AI 代理可以从录制到导出独立完成一整段视频。无论以哪种方式添加 OpenScreen,除编辑工具外,AI 代理都能使用 `listSources`、`startRecording`、`stopRecording`、`setPointerTrack`、`exportVideo` 和 `getFrames`。++**通过上面的服务器**,录制由 OpenScreen 自己完成,就像按下它的录制按钮一样:编辑器关闭,录制栏倒计时后开始录制,录好的内容作为新项目在编辑器中打开,你可以看到每项编辑实时生效。这需要开启**MCP 编辑**,录制结束后,录制栏会恢复你自己的设置。++**作为 stdio 服务器**,则无需任何设置:AI 代理会用 `mcp` 启动应用自身的可执行文件。最快的方式是把下面这段内容粘贴到 Claude Code 中:diff --git a/website/i18n/zh-TW/docusaurus-plugin-content-docs/current/ai-editing.md b/website/i18n/zh-TW/docusaurus-plugin-content-docs/current/ai-editing.mdindex 46c1a2df8..0a425d6dc 100644--- a/website/i18n/zh-TW/docusaurus-plugin-content-docs/current/ai-editing.md+++ b/website/i18n/zh-TW/docusaurus-plugin-content-docs/current/ai-editing.md@@ -67,7 +67,7 @@ ChatGPT 與 GitHub Copilot 的登入選項已**在 1.8.0 中移除**。它們的2. 複製那裡顯示的 **Claude Code** 或 **Codex** 指令,並在終端機中執行。Claude Code 指令中帶有存取權杖。Codex 則改為從 `OPENSCREEN_MCP_TOKEN` 環境變數讀取權杖:請在啟動 Codex 的終端機中設定它。3. 請你的代理進行剪輯,對象可以是 OpenScreen 編輯器中開啟的專案,也可以是清單中的任何其他專案。-這些工具就是內建代理所使用的工具。除非用戶端指定其他專案,否則它們作用於編輯器中開啟的專案:用戶端可以列出所有專案,並讀取或編輯其中任何一個。在你同時開啟 MCP 伺服器區段中的**MCP 編輯**之前,MCP 用戶端只能**讀取**;這個開關與內建代理的**代理編輯**開關各自獨立,預設為關閉。開啟後,每項編輯都會在生效時立即儲存:+這些工具就是內建代理所使用的工具,另外還有錄影、匯出和查看影片的工具([見下文](#letting-an-agent-make-the-whole-video))。除非用戶端指定其他專案,否則它們作用於編輯器中開啟的專案:用戶端可以列出所有專案,並讀取或編輯其中任何一個。在你同時開啟 MCP 伺服器區段中的**MCP 編輯**之前,MCP 用戶端只能**讀取**,它們嘗試的每項編輯、錄影或匯出都會被拒絕。這個開關與內建代理的**代理編輯**開關各自獨立,預設為關閉。開啟後,每項編輯都會在生效時立即儲存:- **在編輯器中開啟的專案上**,編輯可用 `Ctrl/Cmd + Z` 復原。用戶端會被告知在進行一系列編輯之前先儲存檢查點,因此你可以請它們一步將專案還原成原本的樣子,而這一步本身也可以用 `Ctrl/Cmd + Z` 復原。- **在其他任何專案上**,編輯會儲存到它的檔案中,`Ctrl/Cmd + Z` 無法復原。用戶端必須在第一次編輯之前儲存該專案的檢查點,還原到這個檢查點是唯一的復原方式。@@ -76,7 +76,11 @@ ChatGPT 與 GitHub Copilot 的登入選項已**在 1.8.0 中移除**。它們的## 讓代理製作整支影片 {#letting-an-agent-make-the-whole-video}-上述伺服器用於剪輯專案。若要讓代理從錄影到匯出自行製作一整支影片,請改為將 OpenScreen 以 stdio 伺服器的形式加入代理:代理會以 `mcp` 啟動應用程式本身的執行檔。它能使用相同的剪輯工具,另外還有 `listSources`、`startRecording`、`stopRecording`、`setPointerTrack`、`exportVideo` 與 `getFrames`。+代理可以從錄影到匯出自行製作一整支影片。無論以哪種方式加入 OpenScreen,除了剪輯工具之外,代理都能使用 `listSources`、`startRecording`、`stopRecording`、`setPointerTrack`、`exportVideo` 與 `getFrames`。++**透過上述伺服器**,錄影由 OpenScreen 自己完成,就像按下它的錄影按鈕一樣:編輯器會關閉,錄影列倒數後開始錄影,錄好的內容會以新專案在編輯器中開啟,你可以看到每項編輯即時生效。這需要開啟**MCP 編輯**,錄影結束後,錄影列會恢復你自己的設定。++**以 stdio 伺服器的形式加入時**,完全不需要設定:代理會以 `mcp` 啟動應用程式本身的執行檔。最快的方式是將下面這段內容貼到 Claude Code 中: